harvest

harvest is a command for coding agents from Bogzx/seeks. It costs 15 tokens per session (427 once invoked), scanned A, original, MIT.

A command that finds finished or stopped work loops and shows their summaries, commits, and differences from the starting branch.

In plain words
What is it for?
Use it to review completed or halted loops, inspect what changed, and find or open the related pull request.
Why use it?
It helps you find useful changes that may be stranded after a loop stopped before being formally delivered. It never merges changes automatically.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the seeks plugin — 1 skill, 10 commands, 3 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/bogzx/seeks/harvest
Clone the repo
git clone --depth 1 https://github.com/Bogzx/seeks

Or install seeks, the plugin that ships this one along with the rest of its 1 skill, 10 commands, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for harvest

README.md
[![agentmods](https://agentmods.dev/badge/commands/bogzx/seeks/harvest.svg)](https://agentmods.dev/commands/bogzx/seeks/harvest)
Your own site
<a href="https://agentmods.dev/commands/bogzx/seeks/harvest"><img src="https://agentmods.dev/badge/commands/bogzx/seeks/harvest.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 427 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00427
Opus 5 $0.00008 $0.00214
Sonnet 5 $0.00003 $0.00085
Haiku 4.5 $0.00002 $0.00043

Measured 4d ago against content hash 6d213d9fd4c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harvest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/harvest.md · 17 lines

What it actually says

Run shell via the Bash tool. Let each loop's BASE = its base_ref from node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" status-get <name> (fallback: .seeks/config.json base_ref).

Which loops to surface — for $0, or across every dir under .seeks/run/: a loop qualifies if its status done is true OR its branch has real work not yet on the base — git rev-list --count "<BASE>..seeks/<name>" > 0 (a wound-down / halted loop that hit its time budget or iteration cap with committed fixes but never certified — exactly the work that would otherwise be stranded).

For each qualifying loop, show: summary.md (if present), git log --oneline <BASE>..seeks/<name>, git diff --stat <BASE>...seeks/<name>, and the end state from status-get (done, last_change, and the halt reason if any).

Delivery (never auto-merge; the merge is always the user's):

  • L3, done, delivered:true → surface delivery_mode + pr_url — the PR is already open; link it.
  • L3 with real commits but not delivered (wound-down / halted) → offer to open the PR now: node "${CLAUDE_PLUGIN_ROOT}/bin/seeks.mjs" deliver <name> (pushes seeks/<name> + opens a PR; degrades to push-only/local if gh/remote are absent). Ask first, then run it if they say yes.
  • L2 with real commits → recommend review of the branch; offer to push it or open a PR manually if they want.

Recommend review. NEVER merge to the base branch.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 17 lines · 15 tokens per session scan A 6d213d9fd4c7

Subscribe to this mod's changes

harvest is a command published in the GitHub repository Bogzx/seeks (4 stars, last pushed 17d ago), licensed MIT. It adds 15 tokens to every session and 427 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.